What is voila-sdk CLAUDE.md?

A set of project instructions for a grocery-delivery automation software development kit. It explains the project layout, preferred small operations, unofficial web endpoints, login handling, and order-confirmation rules.

Use it when working on the Voila grocery SDK or its related packages. It guides changes to product searches, cart operations, authentication flows, checkout handling, and workspace structure.

It gives an agent the project’s safety and design boundaries before it changes code. This helps avoid broad crawling, unsafe account handling, and placing an order without confirmation.

How dearlordylord/voila-sdk configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to dearlordylord/voila-sdk. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/dearlordylord/voila-sdk/master/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/dearlordylord/voila-sdk

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/dearlordylord/voila-sdk/claude-md/github.svg)](https://agentmods.dev/instructions/dearlordylord/voila-sdk/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/dearlordylord/voila-sdk/claude-md"><img src="https://agentmods.dev/badge/instructions/dearlordylord/voila-sdk/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/dearlordylord/voila-sdk/claude-md"><img src="https://agentmods.dev/badge/instructions/dearlordylord/voila-sdk/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 2,115 This file is loaded in full into every session.

When invoked 2,115 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.02115	$0.02115
Opus 5	$0.01058	$0.01058
Sonnet 5	$0.00423	$0.00423
Haiku 4.5	$0.00212	$0.00212

Measured 10d ago against content hash ccee1c58a3f1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

voila-sdk CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

CLAUDE.md · 189 lines

How it starts

The opening of the file, as written. The whole thing — 189 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Project Instructions

Rules are reflexive: when adding a rule, apply it immediately.

Design Principle: Personal Automation SDK

The primary consumer of this SDK is a coding agent or local automation script assisting one user with Voila grocery workflows. Optimize for predictable, auditable actions over clever hidden behavior. Prefer small, explicit operations such as searchProducts, addCartItems, and getCart over broad workflows that mutate checkout state invisibly.

Voila does not publish a documented third-party customer API. This SDK uses the same same-origin JSON endpoints as the web app. Treat those endpoints as unstable, unofficial, and session-sensitive. Do not crawl broadly, bypass controls, defeat rate limits, or automate account login by storing passwords. Authenticated work must use an interactive browser login/session capture flow.

Never place an order without an explicit caller confirmation step based on the latest server checkout summary.

Workspace Layout

The root package is private. Publishable packages live under packages/:

packages/voila-sdk: @firfi/voila-sdk.
packages/voila-mcp: @firfi/voila-mcp, stdio MCP server.
packages/voila-cli: @firfi/voila-cli, user CLI.

Private draft packages, unpublished and bundled by their consumers:

packages/voila-session-store: @firfi/voila-session-store, the only write path for the session snapshot.

The MCP package owns the shared operation registry used by both MCP tools and CLI commands.

Project Harness

This project follows the ../hulymcp TypeScript/Effect quality harness. These components are mandatory:

Test coverage (vitest.config.ts): v8 provider, 99% thresholds, test:coverage script.
Code duplication (.jscpd.json + jscpd packages/*/src in lint): threshold 2%, console reporter.
Circular dependency detection (madge --circular in circular, wired into check-all).
Pre-commit hooks (.husky/pre-commit): lint-staged plus secrets scanning when gitleaks is installed.
pnpm check-all: build + typecheck + circular + lint + fixture audit + test coverage.
Effect testing: use Effect-aware patterns and keep side effects behind ports/layers.
ESLint: Effect dprint formatting, functional rules, cast bans, mock bans, property-test placement.
Property tests: fast-check imports belong in *.property.test.ts only.
Strict TypeScript: strict, exactOptionalPropertyTypes, noUncheckedIndexedAccess, noImplicitOverride, noFallthroughCasesInSwitch.

Read the full file on GitHub · 189 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

10d ago First seen · 189 lines · 2,115 tokens per session scan A ccee1c58a3f1

Subscribe to this mod's changes

voila-sdk CLAUDE.md is an instructions file published in the GitHub repository dearlordylord/voila-sdk (0 stars, last pushed 16d ago), licensed MIT. It adds 2,115 tokens to every session, about $0.0106 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

voila-sdk: Instructions file for Claude Code